避障
数学优化
计算机科学
非完整系统
解算器
障碍物
拖车
控制理论(社会学)
运动规划
机器人
移动机器人
数学
人工智能
计算机网络
控制(管理)
政治学
法学
作者
Mingzhuo Zhao,Tong Shen,Fanxun Wang,Guodong Yin,Zhiyuan Li,Yang Zhang
出处
期刊:IEEE Transactions on Intelligent Transportation Systems
[Institute of Electrical and Electronics Engineers]
日期:2024-01-01
卷期号:: 1-17
标识
DOI:10.1109/tits.2023.3328245
摘要
Parking semi-trailer train in extremely narrow environments pose challenges due to high nonholonomic constraints, unstable reversing dynamics, and non-convex obstacle avoidance constraints. This paper presents the APTEN (Autonomous Parking of semi-Trailer train in Extremely Narrow environments) with a three-layer framework to address these challenges. In the first layer, we employ a linearized gain scheduling method to create a stable Cl-RRT planner tailored for simplifying unstable reverse dynamics. This planner is adept at promptly warm starting the following homotopy problems. In the second layer, we introduce a novel “dynamics–full dimensional obstacle avoidance” progressive constraint approach. Modifying the constraints of nonlinear programming in separate homotopy problems not only protects the solver from falling into unfeasible local optima but also significantly enhances computational efficiency. In the third layer, a differentiable approach based on convex set separation is employed to establish full-dimensional obstacle avoidance constraints for semi-trailer train. Leveraging the warm start solutions obtained from the previous two layers, the algorithm identifies the optimal solution that strictly adheres to the obstacle avoidance constraints in an extremely narrow environment. The simulation results demonstrate that APTEN excels in parking motion planning within extremely narrow environments, exhibiting the shortest solution time, the highest trajectory quality, and exceptional adaptability to diverse working conditions.
科研通智能强力驱动
Strongly Powered by AbleSci AI